DeepUTF: Locating transcription factor binding sites via interpretable dual-channel encoder-decoder structure
•A novel method (DeepUTF) to predict transcription factor binding sites (TFBSs).•DeepUTF captures other relevant patterns in the transcriptional regulatory network.•The feature learning process of the model is interpretable.•Excellent model predictions compared to TF-DNA complexes in the PDB.•DeepUT...
Saved in:
| Published in: | Pattern recognition Vol. 161; p. 111279 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.05.2025
|
| Subjects: | |
| ISSN: | 0031-3203 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | •A novel method (DeepUTF) to predict transcription factor binding sites (TFBSs).•DeepUTF captures other relevant patterns in the transcriptional regulatory network.•The feature learning process of the model is interpretable.•Excellent model predictions compared to TF-DNA complexes in the PDB.•DeepUTF improves prediction performance compared to state-of-the-art methods.
The accurate location of transcription factor binding sites (TFBSs) is important for the design of synthetic biology components and the realization of precision medicine. Despite the growing use of deep learning for TFBSs prediction, model interpretability remains challenging. We introduce DeepUTF, a novel architecture integrating improved encoder-decoder, swin transformer, and parallel Bi-LSTM, which realizes precise localization of TFBSs and prediction of motifs. We elucidate the effectiveness of the swin transformer in capturing a wide range of dependencies and emphasizing the learning of critical features. Meanwhile, interpretability analysis of the model's output and predictions of TF-DNA binding motifs are conducted, providing a thorough exploration of the model's intrinsic mechanisms and feature learning process. Experiments conducted on 53 ChIP-seq datasets illustrate that DeepUTF surpasses several leading algorithms. The trained model accurately predicts direct and indirect TF-DNA binding motifs. Furthermore, comparisons with the PDB database validate the continuity and accuracy of predictions. |
|---|---|
| AbstractList | •A novel method (DeepUTF) to predict transcription factor binding sites (TFBSs).•DeepUTF captures other relevant patterns in the transcriptional regulatory network.•The feature learning process of the model is interpretable.•Excellent model predictions compared to TF-DNA complexes in the PDB.•DeepUTF improves prediction performance compared to state-of-the-art methods.
The accurate location of transcription factor binding sites (TFBSs) is important for the design of synthetic biology components and the realization of precision medicine. Despite the growing use of deep learning for TFBSs prediction, model interpretability remains challenging. We introduce DeepUTF, a novel architecture integrating improved encoder-decoder, swin transformer, and parallel Bi-LSTM, which realizes precise localization of TFBSs and prediction of motifs. We elucidate the effectiveness of the swin transformer in capturing a wide range of dependencies and emphasizing the learning of critical features. Meanwhile, interpretability analysis of the model's output and predictions of TF-DNA binding motifs are conducted, providing a thorough exploration of the model's intrinsic mechanisms and feature learning process. Experiments conducted on 53 ChIP-seq datasets illustrate that DeepUTF surpasses several leading algorithms. The trained model accurately predicts direct and indirect TF-DNA binding motifs. Furthermore, comparisons with the PDB database validate the continuity and accuracy of predictions. |
| ArticleNumber | 111279 |
| Author | Gao, Xin Yu, Xu Yu, Bin Ding, Pengju He, Shiyue Wang, Jianxin |
| Author_xml | – sequence: 1 givenname: Pengju surname: Ding fullname: Ding, Pengju organization: College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China – sequence: 2 givenname: Jianxin surname: Wang fullname: Wang, Jianxin organization: School of Data Science, Qingdao University of Science and Technology, Qingdao 266061, China – sequence: 3 givenname: Shiyue surname: He fullname: He, Shiyue organization: School of Data Science, Qingdao University of Science and Technology, Qingdao 266061, China – sequence: 4 givenname: Xin surname: Gao fullname: Gao, Xin organization: Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955, Saudi Arabia – sequence: 5 givenname: Xu surname: Yu fullname: Yu, Xu organization: Qingdao Institute of Software, College of Computer Science and technology, China University of Petroleum, Qingdao 266580, China – sequence: 6 givenname: Bin orcidid: 0000-0002-2453-7852 surname: Yu fullname: Yu, Bin email: yubin@qust.edu.cn organization: School of Data Science, Qingdao University of Science and Technology, Qingdao 266061, China |
| BookMark | eNp9kMFOwzAQRH0oEm3hDzj4BxLWTkISDkioUECqxKU9W2tnU1ylTmS7lfh7UsKZ02g1mtHOW7CZ6x0xdicgFSAe7g_pgNH0-1SCzFMhhCzrGZsDZCLJJGTXbBHCAUCUIpdzdnwhGnbb9SPf9AajdXsePbpgvB2i7R1v0cTec21dczGDjRT42SK3LpIfPEXUHfHmhF1ivtA56jg50zfkk4Z-lYfoTyaePN2wqxa7QLd_umS79et29Z5sPt8-Vs-bxMiiiAk1ZQVVoWXW1rU2BAKw1CVSIalswFBFmBXteBS5BIBal7quENFoLAEhW7J86jW-D8FTqwZvj-i_lQB1waQOasKkLpjUhGmMPU0xGn87W_IqGDuOocZ6MlE1vf2_4AfCd3mn |
| Cites_doi | 10.1016/j.patcog.2022.109234 10.1093/bib/bbad231 10.1016/j.patcog.2022.108841 10.1109/ACCESS.2016.2552478 10.1093/bib/bbab273 10.1093/nar/gkw226 10.1038/nmeth.2688 10.1038/nrg3306 10.1093/bioinformatics/btab203 10.1109/TNNLS.2021.3106044 10.1093/nar/gkv1160 10.3390/rs15215264 10.1093/bib/bbad036 10.1109/TCBB.2019.2947461 10.1038/nature13835 10.1016/j.neucom.2019.01.078 10.3390/e22121379 10.1038/nature11232 10.1186/gb-2007-8-2-r24 10.1093/bib/bbab101 10.1016/j.patcog.2022.108825 10.1371/journal.pcbi.1009941 10.1016/j.cell.2018.01.029 10.1038/s41580-022-00566-8 10.1038/s41588-021-00782-6 10.1093/bib/bbaa435 10.1093/nar/gkv416 10.1093/bioinformatics/btw142 10.1093/bioinformatics/btae004 10.1016/j.patcog.2024.110450 10.1016/j.patcog.2021.107975 10.1093/nar/gkg129 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Ltd |
| Copyright_xml | – notice: 2024 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.patcog.2024.111279 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_patcog_2024_111279 S0031320324010306 |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXKI AAXUO AAYFN ABBOA ABDPE ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABWVN ABXDB ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACRPL ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADNMO ADTZH AEBSH AECPX AEFWE AEIPS AEKER AENEX AFJKZ AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAYWO AAYXX ACLOT ACVFH ADCNI AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c255t-ed78085b23f99bce010a7b7ae52e7d0ce8ea35f2e75420009b7b98aaacba70a03 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001392963300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0031-3203 |
| IngestDate | Sat Nov 29 08:20:05 EST 2025 Sat Mar 01 15:46:28 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Swin transformer Transcription factor binding sites Improved encoder-decoder Interpretability |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c255t-ed78085b23f99bce010a7b7ae52e7d0ce8ea35f2e75420009b7b98aaacba70a03 |
| ORCID | 0000-0002-2453-7852 |
| ParticipantIDs | crossref_primary_10_1016_j_patcog_2024_111279 elsevier_sciencedirect_doi_10_1016_j_patcog_2024_111279 |
| PublicationCentury | 2000 |
| PublicationDate | May 2025 2025-05-00 |
| PublicationDateYYYYMMDD | 2025-05-01 |
| PublicationDate_xml | – month: 05 year: 2025 text: May 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Liu, Lin, Cao, Hu, Wei, Zhang, Lin, Guo (bib0024) 2021 Bailey (bib0007) 2021; 37 Glorot, Bengio (bib0032) 2010; 9 Farh, Marson, Zhu, Kleinewietfeld, Housley, Beik, Shoresh, Whitton, Ryan, Shishkin, Hatan, Carrasco-Alfonso, Mayer, Luckey, Patsopoulos, De Jager, Kuchroo, Epstein, Daly, Hafler, Bernstein (bib0002) 2015; 518 Ding, Wang, Zhang, Gao, Liu, Yu (bib0011) 2023; 24 Pei, Wang, Zhang, Wang, Leng, Yang (bib0021) 2022; 131 Xu, Yuan, Ma, Shang, Shi, Zhu (bib0003) 2024; 152 Thurman, Rynes, Humbert, Vierstra, Maurano, Haugen, Sheffield, Stergachis, Wang, Vernot, Garg, John, Sandstrom, Bates, Boatman, Canfield, Diegel, Dunn, Ebersol, Frum, Giste, Johnson, Johnson, Kutyavin, Lajoie, Lee, Lee, London, Lotakis, Neph, Neri, Nguyen, Qu, Reynolds, Roach, Safi, Sanchez, Sanyal, Shafer, Simon, Song, Vong, Weaver, Yan, Zhang, Zhang, Lenhard, Tewari, Dorschner, Hansen, Navas, Stamatoyannopoulos, Iyer, Lieb, Sunyaev, Akey, Sabo, Kaul, Furey, Dekker, Crawford, Stamatoyannopoulos (bib0006) 2012; 489 Buenrostro, Giresi, Zaba, Chang, Greenleaf (bib0005) 2013; 10 He, Schomaker (bib0027) 2021; 117 Zhang, Shen, Huang (bib0034) 2021; 18 Furey (bib0004) 2012; 13 Karolchik, Baertsch, Diekhans, Furey, Hinrichs, Lu, Roskin, Schwartz, Sugnet, Thomas (bib0029) 2003; 31 Zhang, He, Wang, Chen, Guo, Cui, Liu, Huang (bib0015) 2022; 18 Li, Li, Li, Peng, An, He, Li (bib0037) 2018 Mattick, Amaral, Carninci, Carpenter, Chang, Chen, Chen, Dean, Dinger, Fitzgerald (bib0038) 2023; 24 Zhang, Wang, Chen, He, Liu, Huang (bib0033) 2021; 22 Yu, Ding, Gao, Liu, Zhang, Yu (bib0010) 2023; 24 Quang, Xie (bib0012) 2016; 44 Liu, Guo (bib0022) 2019; 337 Sloan, Chan, Davidson, Malladi, Strattan, Hitz, Gabdank, Narayanan, Ho, Lee, Rowe, Dreszer, Roe, Podduturi, Tanaka, Hong, Cherry (bib0030) 2016; 44 Li, Guo, Wang, Yang (bib0019) 2023; 136 Avsec, Weilert, Shrikumar, Krueger, Alexandari, Dalal, Fropf, McAnany, Gagneur, Kundaje, Zeitlinger (bib0014) 2021; 53 Abriata (bib0035) 2017; 18 Zhang, Wang, Li, Pan, Huang (bib0026) 2024; 11 Gong, Long, Yin, Jiao, Wang (bib0025) 2023; 15 Cortiñas-Lorenzo, Pérez-González (bib0031) 2020; 22 Lee (bib0016) 2016; 32 Gupta, Stamatoyannopoulos, Bailey, Noble (bib0028) 2007; 8 Liu, Zibetti, Wan, Wang, Blackshaw, Qian (bib0009) 2017; 18 Adams, Beling, Cogill (bib0017) 2016; 4 Liu, Chen, Du, Jin, Shang (bib0023) 2023; 34 Lambert, Jolma, Campitelli, Das, Yin, Albu, Chen, Taipale, Hughes, Weirauch (bib0001) 2018; 172 Cao, Wang, Yang, Zhou (bib0036) 2024; 40 Zhang, Wang, Zeng, Zhou, Zou (bib0013) 2021; 22 Wang, Yang, Lei, Ul Haq, Zhang, Yang, Francis (bib0018) 2022; 131 Shen, Liu, Song, Yu (bib0020) 2021; 22 Bailey, Johnson, Grant, Noble (bib0008) 2015; 43 Bailey (10.1016/j.patcog.2024.111279_bib0008) 2015; 43 Thurman (10.1016/j.patcog.2024.111279_bib0006) 2012; 489 Liu (10.1016/j.patcog.2024.111279_bib0023) 2023; 34 Pei (10.1016/j.patcog.2024.111279_bib0021) 2022; 131 Liu (10.1016/j.patcog.2024.111279_bib0009) 2017; 18 Zhang (10.1016/j.patcog.2024.111279_bib0026) 2024; 11 Xu (10.1016/j.patcog.2024.111279_bib0003) 2024; 152 Lee (10.1016/j.patcog.2024.111279_bib0016) 2016; 32 Wang (10.1016/j.patcog.2024.111279_bib0018) 2022; 131 Karolchik (10.1016/j.patcog.2024.111279_bib0029) 2003; 31 Ding (10.1016/j.patcog.2024.111279_bib0011) 2023; 24 Cortiñas-Lorenzo (10.1016/j.patcog.2024.111279_bib0031) 2020; 22 Zhang (10.1016/j.patcog.2024.111279_bib0034) 2021; 18 Abriata (10.1016/j.patcog.2024.111279_bib0035) 2017; 18 Gupta (10.1016/j.patcog.2024.111279_bib0028) 2007; 8 Avsec (10.1016/j.patcog.2024.111279_bib0014) 2021; 53 Mattick (10.1016/j.patcog.2024.111279_bib0038) 2023; 24 Furey (10.1016/j.patcog.2024.111279_bib0004) 2012; 13 Sloan (10.1016/j.patcog.2024.111279_bib0030) 2016; 44 Cao (10.1016/j.patcog.2024.111279_bib0036) 2024; 40 Shen (10.1016/j.patcog.2024.111279_bib0020) 2021; 22 Gong (10.1016/j.patcog.2024.111279_bib0025) 2023; 15 Buenrostro (10.1016/j.patcog.2024.111279_bib0005) 2013; 10 Yu (10.1016/j.patcog.2024.111279_bib0010) 2023; 24 Zhang (10.1016/j.patcog.2024.111279_bib0033) 2021; 22 Li (10.1016/j.patcog.2024.111279_bib0037) 2018 Quang (10.1016/j.patcog.2024.111279_bib0012) 2016; 44 Adams (10.1016/j.patcog.2024.111279_bib0017) 2016; 4 Liu (10.1016/j.patcog.2024.111279_bib0024) 2021 Bailey (10.1016/j.patcog.2024.111279_bib0007) 2021; 37 Li (10.1016/j.patcog.2024.111279_bib0019) 2023; 136 Zhang (10.1016/j.patcog.2024.111279_bib0013) 2021; 22 Glorot (10.1016/j.patcog.2024.111279_bib0032) 2010; 9 Farh (10.1016/j.patcog.2024.111279_bib0002) 2015; 518 Lambert (10.1016/j.patcog.2024.111279_bib0001) 2018; 172 He (10.1016/j.patcog.2024.111279_bib0027) 2021; 117 Zhang (10.1016/j.patcog.2024.111279_bib0015) 2022; 18 Liu (10.1016/j.patcog.2024.111279_bib0022) 2019; 337 |
| References_xml | – volume: 18 start-page: 667 year: 2021 end-page: 676 ident: bib0034 article-title: Predicting in-vitro transcription factor binding sites using DNA sequence plus shape publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform. – start-page: 8817 year: 2018 end-page: 8822 ident: bib0037 article-title: Human exonization through differential nucleosome occupancy publication-title: Proceedings of the National Academy of Sciences of the United States of America – start-page: 9992 year: 2021 end-page: 10002 ident: bib0024 article-title: Swin Transformer: hierarchical vision transformer using shifted windows publication-title: Proceedings of the IEEE International Conference on Computer Vision – volume: 22 start-page: bbab101 year: 2021 ident: bib0020 article-title: SAResNet: self-attention residual network for predicting DNA-protein binding publication-title: Brief. Bioinform. – volume: 22 start-page: bbab273 year: 2021 ident: bib0013 article-title: High-resolution transcription factor binding sites prediction improved performance and interpretability by deep learning method publication-title: Brief Bioinform. – volume: 18 start-page: 659 year: 2017 end-page: 669 ident: bib0035 article-title: Structural database resources for biological macromolecules publication-title: Brief. Bioinform. – volume: 18 year: 2022 ident: bib0015 article-title: Base-resolution prediction of transcription factor binding signals by a deep learning framework publication-title: Plos Comput. Biol. – volume: 131 year: 2022 ident: bib0021 article-title: Multi-scale attention based pseudo-3D convolution neural network for Alzheimer's disease diagnosis using structural MRI publication-title: Pattern Recogn. – volume: 43 start-page: W39 year: 2015 end-page: W49 ident: bib0008 article-title: The MEME suite publication-title: Nucleic Acids Res. – volume: 152 year: 2024 ident: bib0003 article-title: Interpretable medical deep framework by logits-constraint attention guiding graph-based multi-scale fusion for Alzheimer's disease analysis publication-title: Pattern Recogn. – volume: 15 start-page: 5264 year: 2023 ident: bib0025 article-title: A hybrid algorithm with swin transformer and convolution for cloud detection publication-title: Remote Sens. – volume: 44 start-page: e107 year: 2016 ident: bib0012 article-title: DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences publication-title: Nucleic Acids Res. – volume: 44 start-page: D726 year: 2016 end-page: D732 ident: bib0030 article-title: ENCODE data at the ENCODE portal publication-title: Nucleic Acids Res. – volume: 131 year: 2022 ident: bib0018 article-title: An entity-weights-based convolutional neural network for large-sale complex knowledge embedding publication-title: Pattern Recogn. – volume: 172 start-page: 650 year: 2018 end-page: 665 ident: bib0001 article-title: The human transcription factors publication-title: Cell – volume: 18 start-page: 1 year: 2017 end-page: 11 ident: bib0009 publication-title: Assessing the Model Transferability For Prediction of Transcription Factor Binding Sites Based On Chromatin Accessibility – volume: 4 start-page: 1642 year: 2016 end-page: 1657 ident: bib0017 article-title: Feature selection for hidden markov models and hidden semi-markov models publication-title: IEEE Access – volume: 489 start-page: 75 year: 2012 end-page: 82 ident: bib0006 article-title: The accessible chromatin landscape of the human genome publication-title: Nature – volume: 53 start-page: 354 year: 2021 end-page: 366 ident: bib0014 article-title: Base-resolution models of transcription-factor binding reveal soft motif syntax publication-title: Nat. Genet. – volume: 13 start-page: 840 year: 2012 end-page: 852 ident: bib0004 article-title: ChIP-seq and beyond: new and improved methodologies to detect and characterize protein-DNA interactions publication-title: Nat. Rev. Genet. – volume: 24 start-page: bbad036 year: 2023 ident: bib0010 article-title: Cooperation of local features and global representations by a dual-branch network for transcription factor binding sites prediction publication-title: Brief. Bioinform. – volume: 24 start-page: bbad231 year: 2023 ident: bib0011 article-title: DeepSTF: predicting transcription factor binding sites by interpretable deep neural networks combining sequence and shape publication-title: Brief. Bioinform. – volume: 37 start-page: 2834 year: 2021 end-page: 2840 ident: bib0007 article-title: STREME: accurate and versatile sequence motif discovery publication-title: Bioinformatics – volume: 9 start-page: 249 year: 2010 end-page: 256 ident: bib0032 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: J. Mach. Learn. Res. – volume: 24 start-page: 430 year: 2023 end-page: 447 ident: bib0038 article-title: Long non-coding RNAs: definitions, functions, challenges and recommendations publication-title: Nat. Rev. Mol. Cell Bio. – volume: 8 year: 2007 ident: bib0028 article-title: Quantifying similarity between motifs publication-title: Genome Biol. – volume: 518 start-page: 337 year: 2015 end-page: 343 ident: bib0002 article-title: Genetic and epigenetic fine mapping of causal autoimmune disease variants publication-title: Nature – volume: 31 start-page: 51 year: 2003 end-page: 54 ident: bib0029 article-title: The UCSC genome browser database publication-title: Nucleic Acids Res. – volume: 337 start-page: 325 year: 2019 end-page: 338 ident: bib0022 article-title: Bidirectional LSTM with attention mechanism and convolutional layer for text classification publication-title: Neurocomputing – volume: 32 start-page: 2196 year: 2016 end-page: 2198 ident: bib0016 article-title: LS-GKM: a new GKM-SVM for large-scale datasets publication-title: Bioinformatics – volume: 10 start-page: 1213 year: 2013 end-page: 1218 ident: bib0005 article-title: Transposition of native chromatin for fast and sensitive epigenomic profiling of open chromatin, DNA-binding proteins and nucleosome position publication-title: Nat. Methods – volume: 22 start-page: bbaa435 year: 2021 ident: bib0033 article-title: Locating transcription factor binding sites by fully convolutional neural network publication-title: Brief. Bioinform. – volume: 117 year: 2021 ident: bib0027 article-title: GR-RNN: global-context residual recurrent neural networks for writer identification publication-title: Pattern Recogn. – volume: 136 year: 2023 ident: bib0019 article-title: Learning spatiotemporal embedding with gated convolutional recurrent networks for translation initiation site prediction publication-title: Pattern Recogn. – volume: 40 start-page: btae004 year: 2024 ident: bib0036 article-title: CircSI-SSL: circRNA-binding site identification based on self-supervised learning publication-title: Bioinformatics – volume: 22 start-page: 1379 year: 2020 ident: bib0031 article-title: Adam and the Ants: on the influence of the optimization algorithm on the detectability of DNN watermarks publication-title: Entropy – volume: 34 start-page: 2156 year: 2023 end-page: 2168 ident: bib0023 article-title: Activated gradients for deep neural networks publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 11 year: 2024 ident: bib0026 article-title: Cross-species prediction of transcription factor binding by adversarial training of a novel nucleotide-level deep neural network publication-title: Adv. Sci. – volume: 136 year: 2023 ident: 10.1016/j.patcog.2024.111279_bib0019 article-title: Learning spatiotemporal embedding with gated convolutional recurrent networks for translation initiation site prediction publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2022.109234 – volume: 24 start-page: bbad231 year: 2023 ident: 10.1016/j.patcog.2024.111279_bib0011 article-title: DeepSTF: predicting transcription factor binding sites by interpretable deep neural networks combining sequence and shape publication-title: Brief. Bioinform. doi: 10.1093/bib/bbad231 – volume: 131 year: 2022 ident: 10.1016/j.patcog.2024.111279_bib0018 article-title: An entity-weights-based convolutional neural network for large-sale complex knowledge embedding publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2022.108841 – volume: 4 start-page: 1642 year: 2016 ident: 10.1016/j.patcog.2024.111279_bib0017 article-title: Feature selection for hidden markov models and hidden semi-markov models publication-title: IEEE Access doi: 10.1109/ACCESS.2016.2552478 – volume: 22 start-page: bbab273 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0013 article-title: High-resolution transcription factor binding sites prediction improved performance and interpretability by deep learning method publication-title: Brief Bioinform. doi: 10.1093/bib/bbab273 – volume: 18 start-page: 1 year: 2017 ident: 10.1016/j.patcog.2024.111279_bib0009 – volume: 9 start-page: 249 year: 2010 ident: 10.1016/j.patcog.2024.111279_bib0032 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: J. Mach. Learn. Res. – volume: 44 start-page: e107 year: 2016 ident: 10.1016/j.patcog.2024.111279_bib0012 article-title: DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences publication-title: Nucleic Acids Res. doi: 10.1093/nar/gkw226 – volume: 10 start-page: 1213 year: 2013 ident: 10.1016/j.patcog.2024.111279_bib0005 article-title: Transposition of native chromatin for fast and sensitive epigenomic profiling of open chromatin, DNA-binding proteins and nucleosome position publication-title: Nat. Methods doi: 10.1038/nmeth.2688 – start-page: 9992 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0024 article-title: Swin Transformer: hierarchical vision transformer using shifted windows – volume: 13 start-page: 840 year: 2012 ident: 10.1016/j.patcog.2024.111279_bib0004 article-title: ChIP-seq and beyond: new and improved methodologies to detect and characterize protein-DNA interactions publication-title: Nat. Rev. Genet. doi: 10.1038/nrg3306 – volume: 37 start-page: 2834 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0007 article-title: STREME: accurate and versatile sequence motif discovery publication-title: Bioinformatics doi: 10.1093/bioinformatics/btab203 – volume: 34 start-page: 2156 year: 2023 ident: 10.1016/j.patcog.2024.111279_bib0023 article-title: Activated gradients for deep neural networks publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2021.3106044 – volume: 44 start-page: D726 year: 2016 ident: 10.1016/j.patcog.2024.111279_bib0030 article-title: ENCODE data at the ENCODE portal publication-title: Nucleic Acids Res. doi: 10.1093/nar/gkv1160 – volume: 15 start-page: 5264 year: 2023 ident: 10.1016/j.patcog.2024.111279_bib0025 article-title: A hybrid algorithm with swin transformer and convolution for cloud detection publication-title: Remote Sens. doi: 10.3390/rs15215264 – volume: 24 start-page: bbad036 year: 2023 ident: 10.1016/j.patcog.2024.111279_bib0010 article-title: Cooperation of local features and global representations by a dual-branch network for transcription factor binding sites prediction publication-title: Brief. Bioinform. doi: 10.1093/bib/bbad036 – volume: 18 start-page: 667 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0034 article-title: Predicting in-vitro transcription factor binding sites using DNA sequence plus shape publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform. doi: 10.1109/TCBB.2019.2947461 – volume: 518 start-page: 337 year: 2015 ident: 10.1016/j.patcog.2024.111279_bib0002 article-title: Genetic and epigenetic fine mapping of causal autoimmune disease variants publication-title: Nature doi: 10.1038/nature13835 – volume: 337 start-page: 325 year: 2019 ident: 10.1016/j.patcog.2024.111279_bib0022 article-title: Bidirectional LSTM with attention mechanism and convolutional layer for text classification publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.01.078 – volume: 22 start-page: 1379 year: 2020 ident: 10.1016/j.patcog.2024.111279_bib0031 article-title: Adam and the Ants: on the influence of the optimization algorithm on the detectability of DNN watermarks publication-title: Entropy doi: 10.3390/e22121379 – volume: 489 start-page: 75 year: 2012 ident: 10.1016/j.patcog.2024.111279_bib0006 article-title: The accessible chromatin landscape of the human genome publication-title: Nature doi: 10.1038/nature11232 – volume: 8 year: 2007 ident: 10.1016/j.patcog.2024.111279_bib0028 article-title: Quantifying similarity between motifs publication-title: Genome Biol. doi: 10.1186/gb-2007-8-2-r24 – start-page: 8817 year: 2018 ident: 10.1016/j.patcog.2024.111279_bib0037 article-title: Human exonization through differential nucleosome occupancy – volume: 22 start-page: bbab101 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0020 article-title: SAResNet: self-attention residual network for predicting DNA-protein binding publication-title: Brief. Bioinform. doi: 10.1093/bib/bbab101 – volume: 131 year: 2022 ident: 10.1016/j.patcog.2024.111279_bib0021 article-title: Multi-scale attention based pseudo-3D convolution neural network for Alzheimer's disease diagnosis using structural MRI publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2022.108825 – volume: 18 year: 2022 ident: 10.1016/j.patcog.2024.111279_bib0015 article-title: Base-resolution prediction of transcription factor binding signals by a deep learning framework publication-title: Plos Comput. Biol. doi: 10.1371/journal.pcbi.1009941 – volume: 172 start-page: 650 year: 2018 ident: 10.1016/j.patcog.2024.111279_bib0001 article-title: The human transcription factors publication-title: Cell doi: 10.1016/j.cell.2018.01.029 – volume: 24 start-page: 430 year: 2023 ident: 10.1016/j.patcog.2024.111279_bib0038 article-title: Long non-coding RNAs: definitions, functions, challenges and recommendations publication-title: Nat. Rev. Mol. Cell Bio. doi: 10.1038/s41580-022-00566-8 – volume: 53 start-page: 354 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0014 article-title: Base-resolution models of transcription-factor binding reveal soft motif syntax publication-title: Nat. Genet. doi: 10.1038/s41588-021-00782-6 – volume: 22 start-page: bbaa435 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0033 article-title: Locating transcription factor binding sites by fully convolutional neural network publication-title: Brief. Bioinform. doi: 10.1093/bib/bbaa435 – volume: 43 start-page: W39 year: 2015 ident: 10.1016/j.patcog.2024.111279_bib0008 article-title: The MEME suite publication-title: Nucleic Acids Res. doi: 10.1093/nar/gkv416 – volume: 32 start-page: 2196 year: 2016 ident: 10.1016/j.patcog.2024.111279_bib0016 article-title: LS-GKM: a new GKM-SVM for large-scale datasets publication-title: Bioinformatics doi: 10.1093/bioinformatics/btw142 – volume: 11 year: 2024 ident: 10.1016/j.patcog.2024.111279_bib0026 article-title: Cross-species prediction of transcription factor binding by adversarial training of a novel nucleotide-level deep neural network publication-title: Adv. Sci. – volume: 40 start-page: btae004 year: 2024 ident: 10.1016/j.patcog.2024.111279_bib0036 article-title: CircSI-SSL: circRNA-binding site identification based on self-supervised learning publication-title: Bioinformatics doi: 10.1093/bioinformatics/btae004 – volume: 152 year: 2024 ident: 10.1016/j.patcog.2024.111279_bib0003 article-title: Interpretable medical deep framework by logits-constraint attention guiding graph-based multi-scale fusion for Alzheimer's disease analysis publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2024.110450 – volume: 117 year: 2021 ident: 10.1016/j.patcog.2024.111279_bib0027 article-title: GR-RNN: global-context residual recurrent neural networks for writer identification publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2021.107975 – volume: 31 start-page: 51 year: 2003 ident: 10.1016/j.patcog.2024.111279_bib0029 article-title: The UCSC genome browser database publication-title: Nucleic Acids Res. doi: 10.1093/nar/gkg129 – volume: 18 start-page: 659 year: 2017 ident: 10.1016/j.patcog.2024.111279_bib0035 article-title: Structural database resources for biological macromolecules publication-title: Brief. Bioinform. |
| SSID | ssj0017142 |
| Score | 2.4707215 |
| Snippet | •A novel method (DeepUTF) to predict transcription factor binding sites (TFBSs).•DeepUTF captures other relevant patterns in the transcriptional regulatory... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 111279 |
| SubjectTerms | Improved encoder-decoder Interpretability Swin transformer Transcription factor binding sites |
| Title | DeepUTF: Locating transcription factor binding sites via interpretable dual-channel encoder-decoder structure |
| URI | https://dx.doi.org/10.1016/j.patcog.2024.111279 |
| Volume | 161 |
| WOSCitedRecordID | wos001392963300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0017142 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF5By4ELb0R5aQ_cokXOrjfr7a2ihYJQFYki5WbtrifFUetETVOFf9_Zh-2mRQiQuORh2Yk182UyOzvzfYS843LqfzXATKW5lzAbMiNlxbgVdioxXyhcFsQm1NFRMZnocdpoXwY5AdU0xXqtF__V1XgMne1HZ__C3d2H4gF8jU7HR3Q7Pv6R4_cBFngnfqn_de4LclEIounjQ9TYGdg6TrT4_ePl4LI2gTsidiCGeaqVOWV-MLiB04Hnu6zgnFUQngeRdzbRkbTZ7TiQdfoBmdSV1O_x7yftlDE0J7NVX8ZPDcEI0nXdnXwY6-I_6p-rDnefTCjqTtJZqVDBZd8WGKtn7QRN364UIrIYMsEzsRGRIz_7regeCw2z9wv8l5qf4OKe5z7k8yhHc4M3-1ukpcw846DXUhvdJdtcSY2hb3vv88HkS7fZpIZ5JJVPt9JOWIY2wNvf9esM5lpWcvyIPEjLCboXYfCY3IHmCXnYSnXQFLmfkrOEil3aYoJuYIJGTNCECRowQRETdAMT9Dom6A1M0A4Tz8j3jwfHHw5ZUtpgDpeUFwwqVWDubbmYam0doMGMssqA5KCqzEEBRsgpvpG5n-3SVlldGGOcNSozmXhOtpp5Ay8ItUXmpBnlhRi5XAttQICTHBNhI0wO-Q5hrfXKRSRUKdtOw1kZrV16a5fR2jtEtSYuU1IYk70SUfHbK1_-85WvyP0ewK_JFloP3pB77vKiXp6_TfC5AoOQjXA |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DeepUTF%3A+Locating+transcription+factor+binding+sites+via+interpretable+dual-channel+encoder-decoder+structure&rft.jtitle=Pattern+recognition&rft.au=Ding%2C+Pengju&rft.au=Wang%2C+Jianxin&rft.au=He%2C+Shiyue&rft.au=Gao%2C+Xin&rft.date=2025-05-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.volume=161&rft_id=info:doi/10.1016%2Fj.patcog.2024.111279&rft.externalDocID=S0031320324010306 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |